They incorporate, in their very architecture, a strong hypothesis: what I learn in one place can be generalized everywhere else.

the simulated annealing algorithm introduces random changes in the parameters, but with a virtual “temperature” that gradually decreases. The probability of a chance event is high at the beginning but steadily declines until the system is frozen in an optimal setting.

it boils down to searching, among myriad possible settings of the internal model, for those that best correspond to the state of the external world.

Attention is the gateway to learning: virtually no information will be memorized if it has not previously been amplified by attention and awareness.

Acetylcholine, on the other hand, attaches itself more generally to all important moments. Its

quivers. Conversely, whenever we need to learn, and learn fast, we can rely on them to optimize our efforts. These pillars are: Attention, which amplifies the information we focus on. Active engagement, an algorithm also called “curiosity,” which encourages our brain to ceaselessly test new hypotheses. Error feedback, which compares our predictions

brains are already organized and knowledgeable.

while error feedback is essential, many children lose confidence and curiosity because their errors are punished rather than corrected.

Well, our synapses are constantly changing, throughout our lives, and these changes reflect what we learn.